[AAAI 2025]Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning
☆42Apr 14, 2025Updated 10 months ago
Alternatives and similar repositories for Math-PUMA
Users that are interested in Math-PUMA are comparing it to the libraries listed below
Sorting:
- MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models☆32Jan 22, 2025Updated last year
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆47Nov 10, 2024Updated last year
- Official Implementation of MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models☆12Nov 1, 2025Updated 4 months ago
- The implement of geometric solver PGPSNet☆30Jan 30, 2025Updated last year
- ☆34Jan 9, 2026Updated 2 months ago
- ☆14Dec 18, 2024Updated last year
- A pipeline for the automatic construction of geometry problems along with step-by-step solutions.☆17Aug 27, 2025Updated 6 months ago
- This repo is the official implementation of "Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision‑Language Models via Geom…☆27Nov 7, 2025Updated 4 months ago
- ☆129Sep 20, 2025Updated 5 months ago
- [ACL 2023] PuMer: Pruning and Merging Tokens for Efficient Vision Language Models☆36Oct 3, 2024Updated last year
- [ICLR'25] Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training☆47Jan 25, 2025Updated last year
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆20May 27, 2025Updated 9 months ago
- This is the Repository for Geometry Problem Solving Method Evaluation☆26Oct 8, 2024Updated last year
- ☆23Aug 17, 2024Updated last year
- Weakly opinionated library for implementing ML models. Less boilerplate, More rigor☆21Jul 1, 2022Updated 3 years ago
- Preference Learning for LLaVA☆59Nov 9, 2024Updated last year
- The first end-to-end deep learning model for explicit plane geometry diagram parsing.☆57Dec 18, 2024Updated last year
- Formal representation and solving for Euclidean plane geometry problems.☆33Dec 19, 2025Updated 2 months ago
- The proposed simulated dataset consisting of 9,536 charts and associated data annotations in CSV format.☆26Feb 22, 2024Updated 2 years ago
- [CVPR 2025] PyTorch implementation of paper "FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training"☆33Jul 8, 2025Updated 8 months ago
- The SVO-Probes Dataset for Verb Understanding☆30Jan 28, 2022Updated 4 years ago
- ☆18Sep 23, 2025Updated 5 months ago
- Paper collections of multi-modal LLM for Math/STEM/Code.☆136Nov 17, 2025Updated 3 months ago
- ACL'24 (Oral) Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback☆77Sep 12, 2024Updated last year
- 表格线检测☆27Sep 3, 2019Updated 6 years ago
- [CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback☆307Sep 11, 2024Updated last year
- Official codebase for the paper "Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space"☆65Dec 17, 2025Updated 2 months ago
- A lightweight driving simulator, written in Julia.☆19Sep 25, 2024Updated last year
- [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"☆97Nov 30, 2025Updated 3 months ago
- [TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"☆147Nov 14, 2024Updated last year
- ☆111Jan 8, 2025Updated last year
- [ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"☆260Apr 14, 2025Updated 10 months ago
- Website nhận diện và trích xuất thông tin từ Chứng Minh Nhân Dân☆11Oct 6, 2022Updated 3 years ago
- Automatically generates captions for an image using Image processing and NLP. Model was trained on Flickr30K dataset.☆11Jun 11, 2020Updated 5 years ago
- the datasets of our paper☆11Feb 26, 2024Updated 2 years ago
- [ACM MM 2023] The released code of paper "Deconfounded Visual Question Generation with Causal Inference"☆11Sep 3, 2024Updated last year
- (NeurIPS 2025) LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search☆21Feb 3, 2026Updated last month
- ☆13Nov 5, 2024Updated last year
- LisanBench is a lightweight benchmark for LLMs that stresses forward planning, vocabulary depth, constraint adherence, attention, and lon…☆23Jun 1, 2025Updated 9 months ago